Skip to content

    Type a page, a command such as keryn scan, or a rule id.

    vercel-ai-sdk-v2

    View as Markdown

    8 rules · Keryn Software Licence · rules 0.8.0 · all packs

    How to read a rule
    Severity
    How bad the finding is if it is real: error fails a default gate, warning and info do not.
    Confidence
    P0 exploitable as written; P1 dangerous in context; P2 a heuristic or a posture check: confirm by reading the code.
    False-positive risk
    low: an exact API or flag, so hits are almost always real; medium: the pattern is legitimate in many programs, so check each hit; high: it finds a lead to confirm, so expect benign hits.
    Edge
    The relationship the finding sits on. reaches: content or traffic gets to a thing; calls: one thing invokes another; reads: one thing reads from another; writes: one thing writes to another; sends: data leaves for another party; grants: authority is given or left unchecked; depends_on: something relies on a component it does not verify; trusts: one party believes another without evidence. The boundary it crosses, when there is one: user->prompt (untrusted input reaching a prompt); model->code (model output reaching code, a shell, a query or a page); secret->outside (a secret leaving the trusted side); supply-chain (code, models or prompts pulled in from outside).
    Taxonomy chips
    References for readers who work in OWASP LLM 2025, OWASP Agentic, CWE or NIST AI RMF. They say where a rule belongs, not that a framework is satisfied.

    seceng.vercelai.streamtext-tools-without-maxsteps

    Section titled “seceng.vercelai.streamtext-tools-without-maxsteps”

    warning typescript, javascript vercel-ai-sdk

    Vercel AI SDK streamText uses tools without maxSteps. Tool-enabled agents should bound step count to reduce runaway execution.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk low: an exact API or flag, so hits are almost always real.

    Edge inspected: grants authority is given or left unchecked.

    CWE-770 LLM06 LLM10 ASI02 ASI08

    Also reported under the older id seceng.loop.vercel-ai-tools-no-maxsteps.

    warning typescript, javascript vercel-ai-sdk

    Vercel AI SDK tool definition lacks an input schema. Tool arguments from the model may be unchecked or unexpectedly shaped.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: reads one thing reads from another.

    CWE-20 LLM06 ASI02

    seceng.vercelai-dangerous-tool-without-approval

    Section titled “seceng.vercelai-dangerous-tool-without-approval”

    warning typescript, javascript vercel-ai-sdk

    Vercel AI SDK tool with dangerous side-effect name executes without visible approval gate.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: grants authority is given or left unchecked.

    CWE-862 LLM06 ASI02

    warning typescript, javascript vercel-ai-sdk

    Vercel AI SDK tool executes shell, file, or network operation from tool arguments without visible allowlist validation.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: calls one thing invokes another.

    CWE-78 CWE-22 CWE-918 LLM06 ASI05 ASI02

    warning typescript, javascript vercel-ai-sdk

    Vercel AI SDK experimental_telemetry appears to record prompts, messages, or metadata that may contain sensitive AI context.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: reads one thing reads from another.

    CWE-532 LLM02 LLM07

    seceng.vercelai-generateobject-without-schema

    Section titled “seceng.vercelai-generateobject-without-schema”

    info typescript, javascript vercel-ai-sdk

    Vercel AI SDK generateObject is used without an explicit schema. Unstructured model output may be trusted as structured data.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: trusts one party believes another without evidence.

    CWE-20 LLM09 LLM05 ASI09

    seceng.vercelai-output-to-database-without-validation

    Section titled “seceng.vercelai-output-to-database-without-validation”

    warning typescript, javascript vercel-ai-sdk

    Vercel AI SDK generated text or object is written to persistent storage without visible validation.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: writes one thing writes to another.

    CWE-20 CWE-915 LLM08 LLM05 ASI06

    seceng.vercelai-stream-without-moderation-buffer

    Section titled “seceng.vercelai-stream-without-moderation-buffer”

    info typescript, javascript vercel-ai-sdk

    Vercel AI SDK streaming result is returned directly without visible moderation, buffering, or output safety filter.

    Confidence P1: dangerous in context. False-positive risk high: it finds a lead to confirm, so expect benign hits.

    Edge inspected: sends data leaves for another party.

    CWE-116 LLM05 ASI06